PH

Phi3-q4_k_m

PhiGGUF by HaitameLaframeUpdated 2024-05-30
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant2.3 GB
Quick answer

Phi3-q4_k_m needs about 6.0 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.3 GB (Q4_K_M) to 4.1 GB (Q8_0).

Phi3-q4_k_m is a 3.82B-parameter Phi model in GGUF format, quantized by HaitameLaframe. Its trained context length is 4K tokens. The repository has 2 quant files, from 2.3 GB (Q4_K_M) to 4.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.3 GB 4.4 GB
Fits Get file →
Q8_04.1 GB 6.2 GB
Fits Get file →

What GPU do you need for Phi3-q4_k_m?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K_M (2.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).

Which Phi3-q4_k_m quant should you choose?

Q4_K_M is the usual starting point for Phi3-q4_k_m: it balances file size and quality well. Here it is a 2.3 GB file.

The Q8_0 file is 4.1 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized byHaitameLaframe
FamilyPhi
Licenseapache-2.0
Downloads (HF)20
Last updated2024-05-30

Frequently asked questions about Phi3-q4_k_m

How much VRAM does Phi3-q4_k_m need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 2.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Phi3-q4_k_m on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi3-q4_k_m GGUF?

It depends on the quant: Q4_K_M is 2.3 GB, Q8_0 is 4.1 GB.

What context length does Phi3-q4_k_m support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download Phi3-q4_k_m GGUF?

The files are on Hugging Face in the HaitameLaframe/Phi3_GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Phi3-q4_k_m use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Phi3_StoryGenerator

Similar models

Browse all →

More from HaitameLaframe

All by HaitameLaframe →

More Phi models

All Phi →

Other small models

All small models →